3D teleimmersive activity classification based on application-system metadata

Aadhar Jain, Ahsan Arefin, Raoul Rivas, Chien Nan Chen, Klara Nahrstedt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Being able to detect and recognize human activities is essential for 3D collaborative applications for efficient quality of service provisioning and device management. A broad range of research has been devoted to analyze media data to identify human activity, which requires the knowledge of data format, application-specific coding technique and computationally expensive image analysis. In this paper, we propose a human activity detection technique based on application generated metadata and related system metadata. Our approach does not depend on specific data format or coding technique. We evaluate our algorithm with different cyber- physical setups, and show that we can achieve very high accuracy (above 97%) by using a good learning model.

Original languageEnglish (US)
Title of host publicationMM 2013 - Proceedings of the 2013 ACM Multimedia Conference
Pages745-748
Number of pages4
DOIs
StatePublished - Nov 18 2013
Event21st ACM International Conference on Multimedia, MM 2013 - Barcelona, Spain
Duration: Oct 21 2013Oct 25 2013

Publication series

NameMM 2013 - Proceedings of the 2013 ACM Multimedia Conference

Other

Other21st ACM International Conference on Multimedia, MM 2013
CountrySpain
CityBarcelona
Period10/21/1310/25/13

Fingerprint

Metadata
Image analysis
Quality of service

Keywords

  • 3D tele-immersion
  • Activity
  • Classification

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Jain, A., Arefin, A., Rivas, R., Chen, C. N., & Nahrstedt, K. (2013). 3D teleimmersive activity classification based on application-system metadata. In MM 2013 - Proceedings of the 2013 ACM Multimedia Conference (pp. 745-748). (MM 2013 - Proceedings of the 2013 ACM Multimedia Conference). https://doi.org/10.1145/2502081.2502194

3D teleimmersive activity classification based on application-system metadata. / Jain, Aadhar; Arefin, Ahsan; Rivas, Raoul; Chen, Chien Nan; Nahrstedt, Klara.

MM 2013 - Proceedings of the 2013 ACM Multimedia Conference. 2013. p. 745-748 (MM 2013 - Proceedings of the 2013 ACM Multimedia Conference).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jain, A, Arefin, A, Rivas, R, Chen, CN & Nahrstedt, K 2013, 3D teleimmersive activity classification based on application-system metadata. in MM 2013 - Proceedings of the 2013 ACM Multimedia Conference. MM 2013 - Proceedings of the 2013 ACM Multimedia Conference, pp. 745-748, 21st ACM International Conference on Multimedia, MM 2013, Barcelona, Spain, 10/21/13. https://doi.org/10.1145/2502081.2502194
Jain A, Arefin A, Rivas R, Chen CN, Nahrstedt K. 3D teleimmersive activity classification based on application-system metadata. In MM 2013 - Proceedings of the 2013 ACM Multimedia Conference. 2013. p. 745-748. (MM 2013 - Proceedings of the 2013 ACM Multimedia Conference). https://doi.org/10.1145/2502081.2502194
Jain, Aadhar ; Arefin, Ahsan ; Rivas, Raoul ; Chen, Chien Nan ; Nahrstedt, Klara. / 3D teleimmersive activity classification based on application-system metadata. MM 2013 - Proceedings of the 2013 ACM Multimedia Conference. 2013. pp. 745-748 (MM 2013 - Proceedings of the 2013 ACM Multimedia Conference).
@inproceedings{db3168788c744ffc85e5b31c78120a4c,
title = "3D teleimmersive activity classification based on application-system metadata",
abstract = "Being able to detect and recognize human activities is essential for 3D collaborative applications for efficient quality of service provisioning and device management. A broad range of research has been devoted to analyze media data to identify human activity, which requires the knowledge of data format, application-specific coding technique and computationally expensive image analysis. In this paper, we propose a human activity detection technique based on application generated metadata and related system metadata. Our approach does not depend on specific data format or coding technique. We evaluate our algorithm with different cyber- physical setups, and show that we can achieve very high accuracy (above 97{\%}) by using a good learning model.",
keywords = "3D tele-immersion, Activity, Classification",
author = "Aadhar Jain and Ahsan Arefin and Raoul Rivas and Chen, {Chien Nan} and Klara Nahrstedt",
year = "2013",
month = "11",
day = "18",
doi = "10.1145/2502081.2502194",
language = "English (US)",
isbn = "9781450324045",
series = "MM 2013 - Proceedings of the 2013 ACM Multimedia Conference",
pages = "745--748",
booktitle = "MM 2013 - Proceedings of the 2013 ACM Multimedia Conference",

}

TY - GEN

T1 - 3D teleimmersive activity classification based on application-system metadata

AU - Jain, Aadhar

AU - Arefin, Ahsan

AU - Rivas, Raoul

AU - Chen, Chien Nan

AU - Nahrstedt, Klara

PY - 2013/11/18

Y1 - 2013/11/18

N2 - Being able to detect and recognize human activities is essential for 3D collaborative applications for efficient quality of service provisioning and device management. A broad range of research has been devoted to analyze media data to identify human activity, which requires the knowledge of data format, application-specific coding technique and computationally expensive image analysis. In this paper, we propose a human activity detection technique based on application generated metadata and related system metadata. Our approach does not depend on specific data format or coding technique. We evaluate our algorithm with different cyber- physical setups, and show that we can achieve very high accuracy (above 97%) by using a good learning model.

AB - Being able to detect and recognize human activities is essential for 3D collaborative applications for efficient quality of service provisioning and device management. A broad range of research has been devoted to analyze media data to identify human activity, which requires the knowledge of data format, application-specific coding technique and computationally expensive image analysis. In this paper, we propose a human activity detection technique based on application generated metadata and related system metadata. Our approach does not depend on specific data format or coding technique. We evaluate our algorithm with different cyber- physical setups, and show that we can achieve very high accuracy (above 97%) by using a good learning model.

KW - 3D tele-immersion

KW - Activity

KW - Classification

UR - http://www.scopus.com/inward/record.url?scp=84887469091&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887469091&partnerID=8YFLogxK

U2 - 10.1145/2502081.2502194

DO - 10.1145/2502081.2502194

M3 - Conference contribution

AN - SCOPUS:84887469091

SN - 9781450324045

T3 - MM 2013 - Proceedings of the 2013 ACM Multimedia Conference

SP - 745

EP - 748

BT - MM 2013 - Proceedings of the 2013 ACM Multimedia Conference

ER -